LION.optimizers.Proj2ProjSolver

Classes

Proj2ProjSolver(model, optimizer, loss_fn[, ...])

Proj2Proj.

---

class LION.optimizers.Proj2ProjSolver.Proj2ProjSolver(model, optimizer, loss_fn, operator_params=None, solver_params=None, model_regularization=None, scheduler=None, scheduler_step='epoch', verbose=1, device=None, seed=0, deterministic=False)

Bases: LIONsolver

Proj2Proj.

The training loss is the mean squared error: the masked self-supervised loss equals the supervised loss up to a constant only for the MSE. loss_fn is only used as the default validation and testing function.

Every solver takes (model, optimizer, loss_fn, operator_params, solver_params, model_regularization, scheduler, scheduler_step, verbose, device, seed, deterministic), in that order (ARSolver has no loss_fn).

operator_params: the parameters of the operator (for CT, the geometry); the model’s, if it has them.

solver_params: the solver’s settings, from default_parameters().

model_regularization: None, or a term added to the training loss of every mini-batch, model_regularization(model, step): a penalty on the model’s weights (step unused) or on what it does with the mini-batch (e.g. LION.losses.jacobian_penalty). step has input (what the model was given), output, target (what the output is compared with; None for solvers without one) and forward (the model as the solver calls it, e.g. with the noise level). Recorded as loss_fn is.

scheduler: a torch learning-rate scheduler made on optimizer (e.g. torch.optim.lr_scheduler.StepLR(optimizer, 30)), or None. It steps after every epoch (scheduler_step="epoch", torch’s convention) or every mini-batch ("batch", e.g. for OneCycleLR). ReduceLROnPlateau steps with the validation value of the epochs that validate, or with the training loss when there is no validation. Its state is saved in checkpoints, and the training record has it and the learning rate of every epoch.

seed: the training seed. When training starts, torch (CPU and CUDA), numpy and Python’s random are seeded with it, so the same solver, model and data give the same training, and checkpoints keep the random state, so a resumed run continues the same way. The randomness within a run (shuffling, noise a solver adds) still changes every batch and epoch. Two runs with the same seed give the same model: use different seeds for an ensemble. None: unseeded.

deterministic: use only deterministic algorithms (torch’s use_deterministic_algorithms, deterministic cuDNN), so that on a GPU two runs with the same seed give exactly the same model, and a resumed run the uninterrupted one. Slower; a few operations then raise (torch names them). It applies to the whole program from here on. Off, GPU runs with the same seed differ slightly (e.g. ~1e-3 in the weights after a few epochs). On a GPU it needs CUBLAS_WORKSPACE_CONFIG=:4096:8 before cuBLAS starts: it is set here if it isn’t (exporting it before the script is surer).

verbose: how much progress is shown. 0: nothing; 1 (default): one progress bar for training (every mini-batch of every epoch, with the epoch, the loss, the last validation value and the time left) and one for testing; 2: also the validation bars and messages (each epoch’s losses, checkpoints, the seed). True is 1, False 0.

get_mask(shape, step)

The masks of a batch of measurements of shape (B, C, H, W): 0 on one cell of every grid_size x grid_size block, the cell cycling with step (the samples seen so far), 1 elsewhere.

fill_mean(y, mask)

y with its masked values (mask 0) replaced by the mean of their four neighbours.

static default_parameters()

grid_size: the masks’ grid (4: one measurement in 16 masked); recon_fn: how measurements are reconstructed (“default”: the operator’s default reconstruction).

mini_batch_step(y, targets)

The loss: the masked measurements filled in, reconstructed, the model’s output projected back, against the measurements on the mask (mean squared error; targets aren’t used: self-supervised).

reconstruct(y)

The model’s reconstructions of the measurements y: of the reconstructions recon_fn makes of them, as in training.

static cite(cite_format='bib')

Where Proj2Proj comes from: its citation, BibTeX (“bib”) or “MLA”.